The Agent Skills Directory

[SAFE]: The skill is entirely descriptive and does not include any executable scripts, tool calls, or network requests. It defines a workflow for an AI agent to categorize git commits and apply Semantic Versioning rules based on user-provided text.- [SAFE]: The instructions explicitly state that the skill cannot directly read git repositories or access files, requiring the user to provide the input data manually, which prevents unauthorized file system access.- [SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were detected. The skill follows best practices for a documentation and release management assistant.

changelog-writer